import pandas as pd
import numpy as np

import matplotlib.pyplot as plt

import plotly.express as px

data = pd.read_csv(r"C:\Users\Iddrisu Bachokun\Desktop\Python\credit_risk_analysis\credit_risk.csv")
data.head()

	Id	Age	Income	Home	Emp_length	Intent	Amount	Rate	Status	Percent_income	Default	Cred_length
0	0	22	59000	RENT	123.0	PERSONAL	35000	16.02	1	0.59	Y	3
1	1	21	9600	OWN	5.0	EDUCATION	1000	11.14	0	0.10	N	2
2	2	25	9600	MORTGAGE	1.0	MEDICAL	5500	12.87	1	0.57	N	3
3	3	23	65500	RENT	4.0	MEDICAL	35000	15.23	1	0.53	N	2
4	4	24	54400	RENT	8.0	MEDICAL	35000	14.27	1	0.55	Y	4

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 32581 entries, 0 to 32580
Data columns (total 12 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   Id              32581 non-null  int64  
 1   Age             32581 non-null  int64  
 2   Income          32581 non-null  int64  
 3   Home            32581 non-null  object 
 4   Emp_length      31686 non-null  float64
 5   Intent          32581 non-null  object 
 6   Amount          32581 non-null  int64  
 7   Rate            29465 non-null  float64
 8   Status          32581 non-null  int64  
 9   Percent_income  32581 non-null  float64
 10  Default         32581 non-null  object 
 11  Cred_length     32581 non-null  int64  
dtypes: float64(3), int64(6), object(3)
memory usage: 3.0+ MB

data.describe()

	Id	Age	Income	Emp_length	Amount	Rate	Status	Percent_income	Cred_length
count	32581.000000	32581.000000	3.258100e+04	31686.000000	32581.000000	29465.000000	32581.000000	32581.000000	32581.000000
mean	16290.006139	27.734600	6.607485e+04	4.789686	9589.371106	11.011695	0.218164	0.170203	5.804211
std	9405.479594	6.348078	6.198312e+04	4.142630	6322.086646	3.240459	0.413006	0.106782	4.055001
min	0.000000	20.000000	4.000000e+03	0.000000	500.000000	5.420000	0.000000	0.000000	2.000000
25%	8145.000000	23.000000	3.850000e+04	2.000000	5000.000000	7.900000	0.000000	0.090000	3.000000
50%	16290.000000	26.000000	5.500000e+04	4.000000	8000.000000	10.990000	0.000000	0.150000	4.000000
75%	24435.000000	30.000000	7.920000e+04	7.000000	12200.000000	13.470000	0.000000	0.230000	8.000000
max	32780.000000	144.000000	6.000000e+06	123.000000	35000.000000	23.220000	1.000000	0.830000	30.000000

data.isna().sum()

Id                   0
Age                  0
Income               0
Home                 0
Emp_length         895
Intent               0
Amount               0
Rate              3116
Status               0
Percent_income       0
Default              0
Cred_length          0
dtype: int64

data['Default'].unique()

array(['Y', 'N'], dtype=object)

data['Cred_length'].unique()

array([ 3,  2,  4,  8,  7,  6,  9, 10,  5, 11, 16, 15, 12, 13, 17, 14, 25,
       28, 27, 22, 19, 29, 23, 26, 20, 21, 30, 24, 18], dtype=int64)

data['Percent_income'].unique()

array([0.59, 0.1 , 0.57, 0.53, 0.55, 0.25, 0.45, 0.44, 0.42, 0.16, 0.41,
       0.37, 0.32, 0.3 , 0.06, 0.29, 0.31, 0.22, 0.52, 0.14, 0.49, 0.13,
       0.5 , 0.35, 0.17, 0.27, 0.33, 0.08, 0.03, 0.21, 0.63, 0.47, 0.4 ,
       0.07, 0.38, 0.34, 0.04, 0.23, 0.15, 0.11, 0.43, 0.51, 0.02, 0.28,
       0.26, 0.19, 0.39, 0.09, 0.05, 0.61, 0.18, 0.6 , 0.01, 0.48, 0.12,
       0.54, 0.56, 0.46, 0.36, 0.24, 0.2 , 0.72, 0.64, 0.69, 0.77, 0.83,
       0.65, 0.67, 0.58, 0.71, 0.68, 0.7 , 0.66, 0.  , 0.76, 0.62, 0.78])

data['Status'].unique()

array([1, 0], dtype=int64)

data['Rate'].isna().sum()

3116

data['Amount'].isna().sum()

0

data['Intent'].unique()

array(['PERSONAL', 'EDUCATION', 'MEDICAL', 'VENTURE', 'HOMEIMPROVEMENT',
       'DEBTCONSOLIDATION'], dtype=object)

data['Emp_length'].isna().sum()

895

df = data[["Age","Income","Home","Emp_length","Intent","Amount","Rate","Status","Percent_income","Default","Cred_length"]].dropna()
df["Deft"] = df.Default # reindexing to chane tthe posiion to the last
df.head()

	Age	Income	Home	Emp_length	Intent	Amount	Rate	Status	Percent_income	Default	Cred_length	Deft
0	22	59000	RENT	123.0	PERSONAL	35000	16.02	1	0.59	Y	3	Y
1	21	9600	OWN	5.0	EDUCATION	1000	11.14	0	0.10	N	2	N
2	25	9600	MORTGAGE	1.0	MEDICAL	5500	12.87	1	0.57	N	3	N
3	23	65500	RENT	4.0	MEDICAL	35000	15.23	1	0.53	N	2	N
4	24	54400	RENT	8.0	MEDICAL	35000	14.27	1	0.55	Y	4	Y

df = df[["Age","Income","Home","Emp_length","Intent","Amount","Rate","Status","Percent_income","Cred_length","Deft"]]
df.head()

	Age	Income	Home	Emp_length	Intent	Amount	Rate	Status	Percent_income	Cred_length	Deft
0	22	59000	RENT	123.0	PERSONAL	35000	16.02	1	0.59	3	Y
1	21	9600	OWN	5.0	EDUCATION	1000	11.14	0	0.10	2	N
2	25	9600	MORTGAGE	1.0	MEDICAL	5500	12.87	1	0.57	3	N
3	23	65500	RENT	4.0	MEDICAL	35000	15.23	1	0.53	2	N
4	24	54400	RENT	8.0	MEDICAL	35000	14.27	1	0.55	4	Y

df.isna().sum()

Age               0
Income            0
Home              0
Emp_length        0
Intent            0
Amount            0
Rate              0
Status            0
Percent_income    0
Cred_length       0
Deft              0
dtype: int64

for label in df.columns[:-1]:
    plt.hist(df[df['Deft']=='Y'][label],color = "red",label="Defaulted",alpha=.7,density=True)
    plt.hist(df[df['Deft']=='N'][label],color = "green",label="Defaulted",alpha=0.7,density=True)
    plt.title(label)
    plt.xlabel(label)
    plt.ylabel("probability")
    plt.legend()
    plt.show()

Box plot visualisation

fig = px.box(df, x= "Deft",
            color = "Deft",
            y ="Age",
            title = "Loan Default status based on Age",
            
            color_discrete_map ={"Y":"red",
                                "N":'green'})

fig.update_traces(quartilemethod='exclusive')

fig = px.box(df, x= "Deft",
            color = "Deft",
            y ="Income",
            title = "Loan Default status based on Income",
            
            color_discrete_map ={"Y":"red",
                                "N":'green'})

fig.update_traces(quartilemethod='exclusive')

fig = px.box(df, x= "Deft",
            color = "Deft",
            y ="Home",
            title = "Loan Default status based on Home",
            
            color_discrete_map ={"Y":"red",
                                "N":'green'})

fig.update_traces(quartilemethod='exclusive')

fig = px.box(df, x= "Deft",
            color = "Deft",
            y ="Emp_length",
            title = "Loan Default status based on Employment",
            
            color_discrete_map ={"Y":"red",
                                "N":'green'})

fig.update_traces(quartilemethod='exclusive')
fig

Pie Chart

home= df["Home"].value_counts()
transactions = home.index
quantity = home.values
fig = px.pie(df,
            values = quantity,
            names = transactions,
            title = "Debter's type of home")
fig.show()

emp= df["Emp_length"].value_counts()
transactions = emp.index
quantity = emp.values
fig = px.pie(df,
            values = quantity,
            names = transactions,
            title = "Debter's type of Employment status")
fig.show()

intent= df["Intent"].value_counts()
transactions = intent.index
quantity = intent.values
fig = px.pie(df,
            values = quantity,
            names = transactions,
            title = "Debter's type of intent")
fig.show()

status= df["Status"].value_counts()
transactions = status.index
quantity = status.values
fig = px.pie(df,
            values = quantity,
            names = transactions,
            title = "Debter's type of Status")
fig.show()

Cnverting the string into number for understaning of the computer

df["Deft"]=df["Deft"].map({"Y":1, 'N':0})

df["Home"] = df["Home"].map({"RENT":1,"MORTGAGE":2,"OWN":3,"OTHER":4})
df["Intent"] =df["Intent"].map({'PERSONAL':1,'EDUCATION':2,'MEDICAL':3,'VENTURE':4,'HOMEIMPROVEMENT':5,'DEBTCONSOLIDATION':6})
df.head()

	Age	Income	Home	Emp_length	Intent	Amount	Rate	Status	Percent_income	Cred_length	Deft
0	22	59000	1	123.0	1	35000	16.02	1	0.59	3	1
1	21	9600	3	5.0	2	1000	11.14	0	0.10	2	0
2	25	9600	2	1.0	3	5500	12.87	1	0.57	3	0
3	23	65500	1	4.0	3	35000	15.23	1	0.53	2	0
4	24	54400	1	8.0	3	35000	14.27	1	0.55	4	1

Training the Data

from sklearn.preprocessing import StandardScaler

train,test,valid = np.split(df.sample(frac=1),[int(0.6*len(df)),int(0.8*len(df))])

def scle_dataset(dataframe):
    
    x = dataframe[dataframe.cols[:-1]].values
    y = dataframe[dataframe.col[-1]].values
    scaler = StandardScaler()
    x = scaler.fit_transform(x)
    
    
    if oversample:
        ros = RandomOverSampler()
        x ,y = ros.fit_resample(x,y)
        data =np.hsatck((x,np.resahpe(y,(-1,1))))
        
        return data ,x,y

print(len(train[train["Deft"]==0]))

14162

print(len(train[train["Deft"]==1]))

3020

Oversampling

from imblearn.over_sampling import RandomOverSampler
from sklearn.preprocessing import StandardScaler

def scale_dataset(dataframe,oversample=False):
    
    x = dataframe[dataframe.columns[:-1]].values
    y = dataframe[dataframe.columns[-1]].values
    scaler = StandardScaler()
    x = scaler.fit_transform(x)
    
    
    if oversample:
        ros = RandomOverSampler()
        x ,y = ros.fit_resample(x,y)
    data =np.hstack((x,np.reshape(y,(-1,1))))
        
    return data ,x,y

train, xtrain, ytrain = scale_dataset(train, oversample=True)
valid, xvalid ,yvalid = scale_dataset(valid, oversample=False)
test, xtest, ytest = scale_dataset(test, oversample=False)

print(len(ytrain==0))

28324

print(len(ytrain==1))

28324

we now see that the data has the same length. We can now go ahead to prediction with the models

from sklearn.metrics import classification_report

from sklearn.svm import SVC

svm_model = SVC()
svm_model.fit(xtrain,ytrain)

SVC()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

y_pred = svm_model.predict(xtest)

print(classification_report(ytest,y_pred))

              precision    recall  f1-score   support

           0       0.98      0.76      0.86      4688
           1       0.46      0.93      0.62      1040

    accuracy                           0.79      5728
   macro avg       0.72      0.84      0.74      5728
weighted avg       0.89      0.79      0.81      5728

we want to use our model to predict some credit risk data

input_data = (23,65500,1,4.0,3,35000,15.23,1,0.53,2)
input_data_np = np.asarray(input_data)
imput_data_re = input_data_np.reshape(1,-1)

pred = svm_model.predict(imput_data_re)
print(pred)
if(pred[0]==0):
    print("The debtor will not default payment")
    
else:
    print("The debtor will default payment")

[0]
The debtor will not default payment

we see that our model is predicting corectly as expected

from sklearn.neighbors import KNeighborsClassifier
knn_model = KNeighborsClassifier()
knn_model.fit(xtrain,ytrain)

KNeighborsClassifier()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

y_pred = knn_model.predict(xtest)

print(classification_report(ytest,y_pred))

              precision    recall  f1-score   support

           0       0.93      0.77      0.84      4688
           1       0.41      0.73      0.52      1040

    accuracy                           0.76      5728
   macro avg       0.67      0.75      0.68      5728
weighted avg       0.83      0.76      0.78      5728

input_data = (24,54400,1,8.0,3,35000,14.27,1,0.55,4)
input_data_np = np.asarray(input_data)
imput_data_re = input_data_np.reshape(1,-1)

pred = knn_model.predict(imput_data_re)
print(pred)
if(pred[0]==0):
    print("The debtor will not default payment")
    
else:
    print("The debtor will default payment")

[1]
The debtor will default payment